Is Markerless More or Less? Comparing a Smartphone Computer Vision Method for Equine Lameness Assessment to Multi-Camera Motion Capture.

Computer vision is a subcategory of artificial intelligence focused on extraction of information from images and video. It provides a compelling new means for objective orthopaedic gait assessment in horses using accessible hardware, such as a smartphone, for markerless motion analysis. This study aimed to explore the lameness assessment capacity of a smartphone single camera (SC) markerless computer vision application by comparing measurements of the vertical motion of the head and pelvis to an optical motion capture multi-camera (MC) system using skin attached reflective markers. Twenty-five horses were recorded with a smartphone (60 Hz) and a 13 camera MC-system (200 Hz) while trotting two times back and forth on a 30 m runway. The smartphone video was processed using artificial neural networks detecting the horse's direction, action and motion of body segments. After filtering, the vertical displacement curves from the head and pelvis were synchronised between systems using cross-correlation. This rendered 655 and 404 matching stride segmented curves for the head and pelvis respectively. From the stride segmented vertical displacement signals, differences between the two minima (MinDiff) and the two maxima (MaxDiff) respectively per stride were compared between the systems. Trial mean difference between systems was 2.2 mm (range 0.0-8.7 mm) for head and 2.2 mm (range 0.0-6.5 mm) for pelvis. Within-trial standard deviations ranged between 3.1-28.1 mm for MC and between 3.6-26.2 mm for SC. The ease of use and good agreement with MC indicate that the SC application is a promising tool for detecting clinically relevant levels of asymmetry in horses, enabling frequent and convenient gait monitoring over time.

Modelling fore- and hindlimb peak vertical force differences in trotting horses using upper body kinematic asymmetry variables.

Differences in peak vertical ground reaction forces (dFzpeak) between contralateral forelimbs and hindlimbs are considered the gold standard for quantifying weight-bearing lameness. However, measuring kinematics for the same purpose is more common and practical. Vertical movement asymmetries (VMA) of the horse's upper body have previously been correlated to fore- and hindlimb lameness. But the combined response of head, withers and pelvis VMA to fore- and hindlimb dFzpeak has not yet been thoroughly investigated. Deriving the kinetic responses from kinematics would help the interpretation and understanding of quantified weight-bearing lameness. In this retrospective study, 103 horses with a wide range of fore- and hindlimb dFzpeak had been trotted on a force-measuring treadmill synchronized with an optical motion capture system. VMA of the head, withers and pelvis as well as dFzpeak were extracted. Multiple linear mixed models and linear regressions of kinematic variables were used to model the dFzpeak. It was hypothesised that all included VMA would have a significant influence on the dFzpeak outcome variables. The results showed a complex relationship between VMA and dFzpeak where both amplitude and timing of the VMA were of importance. On average, the contribution percentage of VMA to fore/hind dFzpeak were 66/34% for head, 76/24% for withers and 33/67% for pelvis. The linear regressions for the fore/hindlimb models achieved mean measurement root mean squared errors of 0.83%/0.82% dFzpeak. These results might help determine the clinical relevance of upper body VMA and distinguish between primary fore, hind, ipsilateral and diagonal weight-bearing lameness.

Roll And Pitch of the Rider's Pelvis During Horseback Riding at Walk on a Circle.

The study investigated between-rider differences in pelvic roll and pitch motion during horseback riding as the horse walked around circles without rein contact (walk on long reins), with rein contact, and with moderate collection. Ten horses were ridden by five riders on left and right 10 m circles, in a partly crossed design, yielding 14 trials. Each trial included each of the three walk variations in both directions. Riders wore an inertial measurement unit (IMU), logging at 100 Hz, dorsally on the pelvis. Pelvic roll and pitch data were split into strides based on data from IMU-sensors on the horse's hind cannons. Data were analyzed using signal decomposition into the fundamental frequency (the stride frequency) and its first two harmonics. Mixed models accounting for the type of walk were used to analyze how riders differed in roll and pitch pelvic motion in two ways: comparing amplitudes of the frequency components and comparing whole stride mean data. Graphically pelvic pitch showed substantial timing and amplitude differences between riders, and this was confirmed statistically. Pelvic roll timing was similar, but amplitude varied between the riders, both graphically and statistically. Individual rider patterns tended to persist across different horses and all exercises. These results suggest that exercises at walk can be ridden with different pelvis pitch timing, a fact that has so far not been discussed in the equestrian literature. Whether pelvic pitch timing affects the horse's performance remains to be investigated.

Reliable and clinically applicable gait event classification using upper body motion in walking and trotting horses.

Objectively assessing horse movement symmetry as an adjunctive to the routine lameness evaluation is on the rise with several commercially available systems on the market. Prerequisites for quantifying such symmetries include knowledge of the gait and gait events, such as hoof to ground contact patterns over consecutive strides. Extracting this information in a robust and reliable way is essential to accurately calculate many kinematic variables commonly used in the field. In this study, optical motion capture was used to measure 222 horses of various breeds, performing a total of 82 664 steps in walk and trot under different conditions, including soft, hard and treadmill surfaces as well as moving on a straight line and in circles. Features were extracted from the pelvis and withers vertical movement and from pelvic rotations. The features were then used in a quadratic discriminant analysis to classify gait and to detect if the left/right hind limb was in contact with the ground on a step by step basis. The predictive model achieved 99.98% accuracy on the test data of 120 horses and 21 845 steps, all measured under clinical conditions. One of the benefits of the proposed method is that it does not require the use of limb kinematics making it especially suited for clinical applications where ease of use and minimal error intervention are a priority. Future research could investigate the extension of this functionality to classify other gaits and validating the use of the algorithm for inertial measurement units.

Riding Soundness-Comparison of Subjective With Objective Lameness Assessments of Owner-Sound Horses at Trot on a Treadmill.

Lameness is a symptom indicative of pain or injury of the locomotor apparatus. Lame horses generally should not be ridden. However, owners' ability to assess lameness has been questioned. This study's aim was to use subjective lameness assessments and objective gait analysis to generate a descriptive overview of movement and weight-bearing asymmetries of owner-sound riding horses. 235 horses were subjectively assessed in a field study, and the owner's perception of their horse's orthopedic health was recorded through an online survey. 69 horses were re-evaluated by gait analysis at an equine hospital. During trot on an instrumented treadmill, the gait was scored by a veterinarian using lameness grades from 0/5 (sound) to 3/5 (moderate lameness visible at trot). Movement asymmetry of the head (HDmin) and pelvis (PDmin) and weight-bearing asymmetry were quantified simultaneously. The prevalence of subjectively scored lameness grade ≥2/5 in one or more limbs was 55% during study part 1 and 74% during study part 2. Movement asymmetry of the head and/or pelvis exceeding HDmin ≥12 mm and/or PDmin ≥6 mm was found in 57% of the horses. 58% showed weight-bearing asymmetries between contralateral front and/or hind limbs of ≥3% body mass. Gait analysis showed considerable variability of movement and weight-bearing asymmetry values, sometimes independent of the clinical lameness grade, especially in the forehand. Several horses with lameness grade ≤1/5 had asymmetry values greater than mentioned thresholds. The analysis of movement and weight-bearing asymmetry revealed that these objective variables did not necessarily act uniformly and therefore should be interpreted with caution.

Influence of Functional Rider and Horse Asymmetries on Saddle Force Distribution During Stance and in Sitting Trot.

Asymmetric forces exerted on the horse's back during riding are assumed to have a negative effect on rider-horse interaction, athletic performance, and health of the horse. Visualized on a saddle pressure mat, they are initially blamed on a nonfitting saddle. The contribution of horse and rider to an asymmetric loading pattern, however, is not well understood. The aim of this study was to investigate the effects of horse and rider asymmetries during stance and in sitting trot on the force distribution on the horse's back using a saddle pressure mat and motion capture analysis simultaneously. Data of 80 horse-rider pairs (HRP) were collected and analyzed using linear (mixed) models to determine the influence of rider and horse variables on asymmetric force distribution. Results showed high variation between HRP. Both rider and horse variables revealed significant relationships to asymmetric saddle force distribution (P < .001). During sitting trot, the collapse of the rider in one hip increased the force on the contralateral side, and the tilt of the rider's upper body to one side led to more force on the same side of the pressure mat. Analyzing different subsets of data revealed that rider posture as well as horse movements and conformation can cause an asymmetric force distribution. Because neither horse nor rider movement can be assessed independently during riding, the interpretation of an asymmetric force distribution on the saddle pressure mat remains challenging, and all contributing factors (horse, rider, saddle) need to be considered.